Text-to-movie authoring of anatomy lessons.

There is a need for a simple yet comprehensive tool to produce and edit pedagogical anatomy video courses, given the widespread usage of multimedia and 3D content in anatomy instruction. Anatomy teachers have minimal control over the present anatomical content generation pipeline. In this research, we provide an authoring tool for instructors that takes text written in the Anatomy Storyboard Language (ASL), a novel domain-specific language (DSL) and produces an animated video. ASL is a formal language that allows users to describe video shots as individual sentences while referencing anatomic structures from a large-scale ontology linked to 3D models. We describe an authoring tool that translates anatomy lessons written in ASL to finite state machines, which are then used to automatically generate 3D animation with the Unity 3D game engine. The proposed text-to-movie authoring tool was evaluated by four anatomy professors to create short lessons on the knee. Preliminary results demonstrate the ease of use and effectiveness of the tool for quickly drafting narrated video lessons in realistic medical anatomy teaching scenarios.

A Generative Audio-Visual Prosodic Model for Virtual Actors.

An important problem in computer animation of virtual characters is the expression of complex mental states during conversation using the coordinated prosody of voice, rhythm, facial expressions, and head and gaze motion. In this work, the authors propose an expressive conversion method for generating natural speech and facial animation in a variety of recognizable attitudes, using neutral speech and animation as input. Their method works by automatically learning prototypical prosodic contours at the sentence level from an original dataset of dramatic attitudes.